Multi-mode Spatial-Temporal Data Modeling with Fully Connected Networks

Spatial-temporal data modeling aims to mine the underlying spatial relationships and temporal dependencies of objects in a system. However, most existing methods focus on the modeling of spatial-temporal data in a single mode, lacking the understanding of multiple modes. Though several methods have been presented to learn the multimode relationships recently, they are built on complicated components with higher model complexities. In this paper, we propose multi-mode spatial-temporal data modeling with simple fully connected networks to bring both effectiveness and efficiency together. Specifically, we design a general cross-mode spatial relationships learning component to adaptively establish connections between multiple modes and propagate information along the learned connections. Moreover, we employ fully connected layers to capture the temporal dependencies and channel correlations, which are conceptually and technically succinct. Experiments on three real-world datasets show that our model can consistently outperform the baselines with lower space and time complexity, opening up a promising direction for modeling spatial-temporal data. The generalizability of the cross-mode relationships learning module is also validated.